Knowledge Base API

Knowledge base id

Need for models for chat use

Current chat

Streaming or not, default streaming response

historical chat

Get top n from the vector library to use as a contextual dialog

Filter weights, only records greater than this value will be used

Model stochasticity

List of array files

Specify the knowledge base to be uploaded

Maximum length of a single paragraph of text in the knowledge base

Adjacent text overlap length in the knowledge base

Specify the participle pattern, either leave it blank or fill it with jina.

Effective when jina is specified as the lexical mode.

Name of the knowledge base

Knowledge Base Description

chatchat or rag_nano
chatchat is a traditional vector-based knowledge base
rag_nano is a knowledge base based on knowledge graphs

optional；embedding data processing model

optional；LLM model

The ID of the model to be used. For detailed information on which models are applicable to the chat API, please view Model endpoint compatibility

Generate messages in chat format for chat completions.

What sampling temperature to use, ranging from 0 to 2. Higher values, such as 0.8, will make the output more random, while lower values, like 0.2, will make it more focused and deterministic. We generally recommend adjusting either this or top_p, but not both simultaneously.

An alternative to temperature sampling is nucleus sampling, where the model considers tokens within the top_p probability mass. For instance, top_p = 0.1 means only tokens within the top 10% probability mass are considered. We recommend adjusting either this or temperature, but not both simultaneously.

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by data: [DONE] message. For Example Code.，Please view OpenAI Cookbook.

Up to 4 sequences where the API will stop generating further tokens.

The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model’s context length.

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics. See more information about frequency and presence penalties.

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim. See more information about frequency and presence penalties.

Modify the likelihood of specific tokens appearing in the completion. This can be done by providing a JSON object that maps tokens (identified by their token IDs in the tokenizer) to a bias value ranging from -100 to 100. Mathematically, this bias is added to the logits generated by the model before sampling. The exact effect varies depending on the model, but values between -1 and 1 will slightly decrease or increase the likelihood of selection, while values like -100 or 100 will either ban or exclusively select the relevant token.

A unique identifier representing your end users, which helps OpenAI monitor and detect abuse. View more

LLM name for meta chunking

File language, options are zh/en, default is zh

Whether to merge dynamically, options are yes/no, default is no